Bayesian Learning for Neural Networks

ISBN-13: 9780387947242 / Angielski / Miękka / 1996 / 204 str.

Radford M. Neal;Neal

Opis

Demonstrates how Bayesian methods allow complex neural network models to be used without the overfitting that can occur with traditional training methods. The text presents an insight into complex Baynesian models by a theoretical investigation of priors over functions that underlie them.

Spis treści

Preface; 1: Introduction; 2: Priors for Infinite Networks; 3: Monte Carlo Implementation; 4: Evaluation of Neural Network Models; 5: Conclusions and Further Work; A: Details of the Implementation; B: Obtaining the Software; Bibliography; Index